Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    explaining specific subjects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     unui
    0.41
     zwei
    0.39
    senz
    0.38
     deux
    0.38
     ដ
    0.38
     einem
    0.38
     einer
    0.37
     mehrerer
    0.36
     mehrere
    0.36
     isang
    0.36
    POSITIVE LOGITS
     happenings
    0.50
     history
    0.49
     policies
    0.47
     laws
    0.45
     FAQs
    0.45
     philosophy
    0.44
     options
    0.44
     theology
    0.44
     issues
    0.43
     Geology
    0.43
    Act Density 0.334%

    No Known Activations